LICENSE
NOTICE
README.md
pyproject.toml
app/cli.py
app/workflows.py
app/commands/__init__.py
app/commands/audit.py
app/commands/benchmark.py
app/commands/doctor.py
app/commands/merge.py
app/commands/test.py
app/commands/validate.py
indw.egg-info/PKG-INFO
indw.egg-info/SOURCES.txt
indw.egg-info/dependency_links.txt
indw.egg-info/entry_points.txt
indw.egg-info/requires.txt
indw.egg-info/top_level.txt
src/indw/__init__.py
src/indw/_compat.py
src/indw/clean/__init__.py
src/indw/clean/corpus.py
src/indw/clean/artifact/calibrate.py
src/indw/clean/artifact/confidence.py
src/indw/clean/artifact/decompose.py
src/indw/clean/artifact/discovery_clean.py
src/indw/clean/artifact/discovery_config.py
src/indw/clean/artifact/discovery_corpus.py
src/indw/clean/artifact/discovery_engine.py
src/indw/clean/artifact/discovery_registry.py
src/indw/clean/artifact/discovery_structural.py
src/indw/clean/artifact/discovery_validation.py
src/indw/clean/artifact/engine.py
src/indw/clean/artifact/evidence.py
src/indw/clean/artifact/evidence_cache.py
src/indw/clean/artifact/evidence_engine.py
src/indw/clean/artifact/evidence_features.py
src/indw/clean/artifact/evidence_model.py
src/indw/clean/artifact/evidence_util.py
src/indw/clean/artifact/novelty.py
src/indw/clean/artifact/positional.py
src/indw/clean/artifact/registry.py
src/indw/clean/artifact/safeguards.py
src/indw/clean/artifact/strip.py
src/indw/clean/artifact/trim.py
src/indw/clean/document/adaptive.py
src/indw/clean/document/boilerplate.py
src/indw/clean/document/clean.py
src/indw/clean/document/code_preservation.py
src/indw/clean/document/compression.py
src/indw/clean/document/config.py
src/indw/clean/document/conversation.py
src/indw/clean/document/dedup.py
src/indw/clean/document/html.py
src/indw/clean/document/license.py
src/indw/clean/document/metrics.py
src/indw/clean/document/normalize.py
src/indw/clean/document/patterns.py
src/indw/clean/document/segment.py
src/indw/clean/document/stage_manifest.py
src/indw/clean/document/stats.py
src/indw/clean/document/ui.py
src/indw/clean/document/validate.py
src/indw/clean/document/value.py
src/indw/clean/gate/evaluate.py
src/indw/clean/gate/policy.py
src/indw/clean/meta/clean.py
src/indw/clean/meta/foundation.py
src/indw/clean/meta/patterns.py
src/indw/clean/meta/stats.py
src/indw/clean/meta/strip.py
src/indw/clean/semantic/boilerplate.py
src/indw/clean/semantic/classifier.py
src/indw/clean/semantic/clean.py
src/indw/clean/semantic/config.py
src/indw/clean/semantic/embedded.py
src/indw/clean/semantic/fingerprints.py
src/indw/clean/semantic/ocr_normalize.py
src/indw/clean/semantic/pipeline.py
src/indw/clean/semantic/report.py
src/indw/clean/semantic/routing.py
src/indw/clean/semantic/scoring.py
src/indw/clean/semantic/section_artifacts.py
src/indw/clean/semantic/spec.py
src/indw/clean/semantic/structure.py
src/indw/clean/semantic/thresholds.py
src/indw/clean/structure/__init__.py
src/indw/clean/structure/extract.py
src/indw/clean/structure/labeled_qa.py
src/indw/clean/structure/reference_sections.py
src/indw/config/__init__.py
src/indw/config/defaults.py
src/indw/config/loader.py
src/indw/config/resolve.py
src/indw/config/validation.py
src/indw/dedup/__init__.py
src/indw/dedup/exact.py
src/indw/dedup/fuzzy.py
src/indw/dedup/normalize.py
src/indw/dedup/replay.py
src/indw/dedup/semantic.py
src/indw/dedup/storage.py
src/indw/dedup/backends/__init__.py
src/indw/dedup/backends/fuzzy.py
src/indw/dedup/embed/__init__.py
src/indw/dedup/embed/ann.py
src/indw/dedup/embed/candidate.py
src/indw/dedup/embed/cluster.py
src/indw/dedup/embed/config.py
src/indw/dedup/embed/contracts.py
src/indw/dedup/embed/e5.py
src/indw/dedup/embed/pipeline.py
src/indw/dedup/embed/providers.py
src/indw/dedup/embed/representative.py
src/indw/dedup/embed/similarity.py
src/indw/dedup/embed/threshold.py
src/indw/dedup/embed/pools/__init__.py
src/indw/dedup/embed/pools/gpu_worker.py
src/indw/dedup/service/__init__.py
src/indw/dedup/service/exact_shard.py
src/indw/extract/__init__.py
src/indw/extract/assess/doc_type.py
src/indw/extract/assess/engine.py
src/indw/extract/assess/feedback.py
src/indw/extract/assess/metrics.py
src/indw/extract/assess/quality.py
src/indw/extract/core/clean.py
src/indw/extract/core/context.py
src/indw/extract/core/profile.py
src/indw/extract/core/units.py
src/indw/extract/nav/context.py
src/indw/extract/nav/metrics.py
src/indw/extract/nav/template.py
src/indw/extract/roles/education.py
src/indw/extract/roles/forum.py
src/indw/extract/roles/publication.py
src/indw/extract/roles/units.py
src/indw/extract/sections/boundaries.py
src/indw/extract/sections/classify.py
src/indw/extract/sections/integrity.py
src/indw/extract/sections/quality.py
src/indw/extract/sections/scratch.py
src/indw/extract/sections/semantic.py
src/indw/extract/structure/aggregate.py
src/indw/extract/structure/analyze.py
src/indw/extract/structure/document.py
src/indw/extract/structure/inline.py
src/indw/extract/structure/recovery.py
src/indw/extract/structure/segment.py
src/indw/filter/__init__.py
src/indw/filter/content/code.py
src/indw/filter/content/domain.py
src/indw/filter/content/filters.py
src/indw/filter/content/metadata.py
src/indw/filter/decide/calibrate.py
src/indw/filter/decide/curator.py
src/indw/filter/decide/engine.py
src/indw/filter/decide/policy.py
src/indw/filter/decide/threshold.py
src/indw/filter/gate/diagnostics.py
src/indw/filter/gate/quality.py
src/indw/filter/gate/reports.py
src/indw/filter/gate/scorer.py
src/indw/filter/language/bridge.py
src/indw/filter/language/confidence.py
src/indw/filter/language/config.py
src/indw/filter/language/detect.py
src/indw/filter/language/fast_detector.py
src/indw/filter/language/mixed.py
src/indw/filter/language/reports.py
src/indw/filter/language/script.py
src/indw/filter/language/script_metrics.py
src/indw/filter/language/script_opt.py
src/indw/filter/language/script_orch.py
src/indw/filter/language/script_policy.py
src/indw/filter/language/script_table.py
src/indw/filter/language/stats.py
src/indw/filter/language/telemetry.py
src/indw/filter/language/token_metrics.py
src/indw/filter/language/validation.py
src/indw/filter/license/classifier.py
src/indw/filter/license/config.py
src/indw/filter/license/detector.py
src/indw/filter/license/manifest.py
src/indw/filter/license/normalize.py
src/indw/filter/license/policy.py
src/indw/filter/license/record.py
src/indw/filter/license/reports.py
src/indw/filter/license/schema.py
src/indw/filter/license/source_policy.py
src/indw/filter/pii/config.py
src/indw/filter/pii/context.py
src/indw/filter/pii/detect.py
src/indw/filter/pii/entities.py
src/indw/filter/pii/redaction.py
src/indw/filter/pii/reports.py
src/indw/filter/pii/risk.py
src/indw/filter/pii/secrets.py
src/indw/filter/pii/validation.py
src/indw/filter/refine/audit.py
src/indw/filter/refine/corpus.py
src/indw/filter/refine/processor.py
src/indw/filter/refine/rewrite.py
src/indw/filter/refine/settings.py
src/indw/filter/refine/truncation.py
src/indw/filter/score/adaptive.py
src/indw/filter/score/analysis.py
src/indw/filter/score/artifacts.py
src/indw/filter/score/builder.py
src/indw/filter/score/canonical.py
src/indw/filter/score/continuous.py
src/indw/filter/score/engine.py
src/indw/filter/score/signals.py
src/indw/filter/score/types.py
src/indw/filter/spec/document.py
src/indw/filter/spec/export.py
src/indw/filter/spec/pipeline.py
src/indw/filter/spec/quality.py
src/indw/filter/spec/validate.py
src/indw/filter/stage0/admission.py
src/indw/filter/stage0/audit.py
src/indw/filter/stage0/engine.py
src/indw/filter/stage0/verify.py
src/indw/filter/toxicity/classifier_labels.py
src/indw/filter/toxicity/config.py
src/indw/filter/toxicity/context.py
src/indw/filter/toxicity/detect.py
src/indw/filter/toxicity/patterns.py
src/indw/filter/toxicity/reports.py
src/indw/filter/toxicity/rule_scorer.py
src/indw/filter/toxicity/rules.py
src/indw/filter/toxicity/scorer.py
src/indw/filter/toxicity/validation.py
src/indw/ingest/__init__.py
src/indw/ingest/download.py
src/indw/ingest/format.py
src/indw/ingest/hash.py
src/indw/ingest/hf_datasets.py
src/indw/ingest/hf_env.py
src/indw/ingest/log.py
src/indw/ingest/resume.py
src/indw/ingest/run.py
src/indw/ingest/sink.py
src/indw/ingest/transcript.py
src/indw/schedule/__init__.py
src/indw/schedule/core.py
src/indw/schedule/admission/__init__.py
src/indw/schedule/admission/tier01.py
src/indw/schedule/admission/tiers.py
src/indw/schedule/admission/tracker.py
src/indw/schedule/apply/coordinator.py
src/indw/schedule/apply/dedup.py
src/indw/schedule/apply/lifecycle.py
src/indw/schedule/apply/merge.py
src/indw/schedule/apply/serialize.py
src/indw/schedule/architecture/__init__.py
src/indw/schedule/architecture/classify.py
src/indw/schedule/architecture/graph.py
src/indw/schedule/architecture/ownership.py
src/indw/schedule/architecture/resources.py
src/indw/schedule/backends/__init__.py
src/indw/schedule/backends/config.py
src/indw/schedule/backends/contract.py
src/indw/schedule/backends/dask.py
src/indw/schedule/backends/factory.py
src/indw/schedule/backends/local.py
src/indw/schedule/backends/multiprocess.py
src/indw/schedule/backends/thread.py
src/indw/schedule/config/hardware.py
src/indw/schedule/config/pin.py
src/indw/schedule/config/policy.py
src/indw/schedule/config/resolve.py
src/indw/schedule/config/tune.py
src/indw/schedule/dispatch/alloc.py
src/indw/schedule/dispatch/lanes.py
src/indw/schedule/dispatch/parallel.py
src/indw/schedule/dispatch/workers.py
src/indw/schedule/graph/__init__.py
src/indw/schedule/graph/artifacts.py
src/indw/schedule/graph/config.py
src/indw/schedule/graph/envelope.py
src/indw/schedule/graph/queues.py
src/indw/schedule/graph/runner.py
src/indw/schedule/ingest/coordinator.py
src/indw/schedule/intel/coordination.py
src/indw/schedule/intel/fingerprints.py
src/indw/schedule/intel/genome.py
src/indw/schedule/intel/hardware.py
src/indw/schedule/intel/incremental.py
src/indw/schedule/intel/inheritance.py
src/indw/schedule/intel/lci_graph.py
src/indw/schedule/intel/lci_router.py
src/indw/schedule/intel/merge_session.py
src/indw/schedule/intel/pci.py
src/indw/schedule/intel/promotion.py
src/indw/schedule/intel/router.py
src/indw/schedule/intel/scores.py
src/indw/schedule/intel/session.py
src/indw/schedule/intel/store.py
src/indw/schedule/intel/pools/__init__.py
src/indw/schedule/intel/pools/acim.py
src/indw/schedule/intel/pools/pci.py
src/indw/schedule/mix/config.py
src/indw/schedule/mix/curriculum.py
src/indw/schedule/mix/mixture_planner.py
src/indw/schedule/mix/plan.py
src/indw/schedule/mix/sampler.py
src/indw/schedule/mix/telemetry.py
src/indw/schedule/monitor/audit.py
src/indw/schedule/monitor/budget.py
src/indw/schedule/monitor/cost.py
src/indw/schedule/monitor/cpu.py
src/indw/schedule/monitor/doc.py
src/indw/schedule/monitor/invariants.py
src/indw/schedule/monitor/live.py
src/indw/schedule/monitor/obs.py
src/indw/schedule/monitor/pipeline_exporter.py
src/indw/schedule/read/gates.py
src/indw/schedule/read/ingest.py
src/indw/schedule/read/preprocess.py
src/indw/schedule/read/probe.py
src/indw/schedule/read/sources.py
src/indw/schedule/routing/__init__.py
src/indw/schedule/routing/admission.py
src/indw/schedule/row/index.py
src/indw/schedule/row/provenance.py
src/indw/schedule/row/reject.py
src/indw/schedule/row/resolve.py
src/indw/schedule/row/signals.py
src/indw/schedule/stages/__init__.py
src/indw/schedule/stages/artifact_cleaning.py
src/indw/schedule/stages/classification.py
src/indw/schedule/stages/contracts.py
src/indw/schedule/stages/curator.py
src/indw/schedule/stages/engine.py
src/indw/schedule/stages/knowledge.py
src/indw/schedule/stages/normalization.py
src/indw/schedule/stages/quality.py
src/indw/schedule/stages/rewrite.py
src/indw/schedule/stages/runner.py
src/indw/schedule/stages/structural_repair.py
src/indw/schedule/stages/validation.py
src/indw/schedule/stages/pools/__init__.py
src/indw/schedule/stages/pools/chain.py
src/indw/schedule/stages/pools/clean.py
src/indw/schedule/stages/pools/filter.py
src/indw/schedule/stages/pools/preprocess.py
src/indw/schedule/stages/pools/stage0.py
src/indw/schedule/state/artifacts.py
src/indw/schedule/state/checkpoint.py
src/indw/schedule/state/context.py
src/indw/schedule/state/lock.py
src/indw/schedule/state/sessions.py
src/indw/schedule/state/setup.py
src/indw/schedule/state/survivor.py
src/indw/store/corpus/manifest.py
src/indw/store/corpus/registry.py
src/indw/store/eval/compare.py
src/indw/store/eval/config.py
src/indw/store/eval/decision.py
src/indw/store/eval/diversity.py
src/indw/store/eval/evaluator.py
src/indw/store/eval/knowledge.py
src/indw/store/eval/metrics.py
src/indw/store/eval/reports.py
src/indw/store/eval/scoring.py
src/indw/store/eval/validation.py
src/indw/store/export/config.py
src/indw/store/export/export_items.py
src/indw/store/export/fast_export.py
src/indw/store/export/memmap_stream.py
src/indw/store/export/packed_stream.py
src/indw/store/export/pipeline.py
src/indw/store/export/prefetch.py
src/indw/store/export/replay_export.py
src/indw/store/export/shard_io.py
src/indw/store/export/shard_meta.py
src/indw/store/export/splits.py
src/indw/store/export/packing/__init__.py
src/indw/store/export/packing/binpack.py
src/indw/store/export/packing/collate.py
src/indw/store/export/packing/config.py
src/indw/store/io/atomic.py
src/indw/store/io/cache.py
src/indw/store/io/columnar.py
src/indw/store/io/json_codec.py
src/indw/store/io/jsonl.py
src/indw/store/io/retry.py
src/indw/tools/__init__.py
src/indw/tools/metrics/alerts.py
src/indw/tools/metrics/config.py
src/indw/tools/metrics/pipeline_health.py
src/indw/tools/metrics/recovery.py
src/indw/tools/metrics/regression.py
src/indw/tools/metrics/reject_log.py
src/indw/tools/metrics/reports.py
src/indw/tools/metrics/snapshot.py
src/indw/tools/metrics/stage_profile.py
src/indw/tools/metrics/storage.py
src/indw/tools/metrics/trends.py
src/indw/tools/metrics/validation.py
src/indw/tools/reports/__init__.py
src/indw/tools/reports/admission_cost.py
src/indw/tools/reports/batch_efficiency_audit.py
src/indw/tools/reports/dask_integration.py
src/indw/tools/reports/execution_consolidation.py
src/indw/tools/reports/foundation_cost.py
src/indw/tools/reports/heavy_cost.py
src/indw/tools/reports/library_migration.py
src/indw/tools/reports/pipeline_audit.py
src/indw/tools/reports/pipeline_tune_report.py
src/indw/tools/reports/production_scale_report.py
src/indw/tools/reports/stabilization_audit.py
src/indw/tools/reports/stage0_cost.py
src/indw/tools/reports/audit_left/artifact_leakage.py
src/indw/tools/reports/audit_left/pipeline.py
src/indw/tools/reports/audit_left/validation.py
src/indw/tools/reports/benchmark/__init__.py
src/indw/tools/reports/benchmark/scale.py
src/indw/tools/reports/fast/__init__.py
src/indw/tools/reports/fast/analyze.py
src/indw/tools/reports/fast/patterns.py
src/indw/tools/reports/fast/report.py
src/indw/tools/reports/fast/sample.py
src/indw/tools/reports/fast/stats.py
src/indw/util/hf_tokenizers.py
src/indw/util/stable_hash.py
src/indw/util/stats.py